Short-Term Intersection Traffic Flow Forecasting

Qu, Wenrui; Li, Jinhong; Lan, Yang; Li, Delin; Li, Shasha; Zhao, Qun; Qi, Yi

doi:10.3390/su12198158

Cited by 22 publications

(21 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…K-Nearest Neighbors (KNN) is a non-parametric method which can be used for regression and classification [43]. In this study, KNN was used for regression.…”

Section: K-nearest Neighborsmentioning

confidence: 99%

Evaluation of Rainfall Erosivity Factor Estimation Using Machine and Deep Learning Models

Lee

Hong

et al. 2021

Water

View full text Add to dashboard Cite

Rainfall erosivity factor (R-factor) is one of the Universal Soil Loss Equation (USLE) input parameters that account for impacts of rainfall intensity in estimating soil loss. Although many studies have calculated the R-factor using various empirical methods or the USLE method, these methods are time-consuming and require specialized knowledge for the user. The purpose of this study is to develop machine learning models to predict the R-factor faster and more accurately than the previous methods. For this, this study calculated R-factor using 1-min interval rainfall data for improved accuracy of the target value. First, the monthly R-factors were calculated using the USLE calculation method to identify the characteristics of monthly rainfall-runoff induced erosion. In turn, machine learning models were developed to predict the R-factor using the monthly R-factors calculated at 50 sites in Korea as target values. The machine learning algorithms used for this study were Decision Tree, K-Nearest Neighbors, Multilayer Perceptron, Random Forest, Gradient Boosting, eXtreme Gradient Boost, and Deep Neural Network. As a result of the validation with 20% randomly selected data, the Deep Neural Network (DNN), among seven models, showed the greatest prediction accuracy results. The DNN developed in this study was tested for six sites in Korea to demonstrate trained model performance with Nash–Sutcliffe Efficiency (NSE) and the coefficient of determination (R2) of 0.87. This means that our findings show that DNN can be efficiently used to estimate monthly R-factor at the desired site with much less effort and time with total monthly precipitation, maximum daily precipitation, and maximum hourly precipitation data. It will be used not only to calculate soil erosion risk but also to establish soil conservation plans and identify areas at risk of soil disasters by calculating rainfall erosivity factors.

show abstract

“…K-Nearest Neighbors (KNN) is a non-parametric method which can be used for regression and classification [43]. In this study, KNN was used for regression.…”

Section: K-nearest Neighborsmentioning

confidence: 99%

Evaluation of Rainfall Erosivity Factor Estimation Using Machine and Deep Learning Models

Lee

Hong

et al. 2021

Water

View full text Add to dashboard Cite

show abstract

“…Using appropriate vegetation and soil amendments can effectively improve the ecological environment [3][4][5]. However, the water for vegetation restoration is in short supply in the northwest China [6][7][8]. To solve this problem, improving water use efficiency and seeking innovations in water resources management are feasible solutions [7].…”

Section: Introductionmentioning

confidence: 99%

Reclaimed water application to vegetation restoration in mining area: Determination of water quality standards and optimization of moderate treatment technology

et al. 2021

View full text Add to dashboard Cite

Water shortage severely restricts vegetation restoration of mining area in the northwest China. Moderate treatment of reclaimed water is essential for improving the local ecological environment. In this study, relevant water quality standards issued by the states and research results were comprehensively considered to propose a reclaimed water quality standard suitable for vegetation restoration of mining area. The available domestic sewage and mine water was moderately treated by hybrid biological reactor system and nanofiltration membrane system, respectively. The effluent quality meet the requirement of reclaimed water quality standards in this study. This study provides theoretical support for vegetation restoration of mining area.

show abstract

“…Optimized K Value Based on the distance calculated in Equation ( 2), the K nearest neighbors (the K historical days that have the traffic conditions most similar to the traffic condition at the targeted time t of the prediction day) can be selected. In the basic KNN model that was developed by Qu et al [21], a given k value (K = 10) was used. To improve the model prediction, in this study, different K values from 7 to 15 were tested and the K values that resulted in the lowest prediction error were selected for predicting the traffic flow rate at the study intersection.…”

mentioning

confidence: 99%

“…Improved Prediction Algorithm In the basic KNN model developed by Qu et al [21], the average traffic flow rate of the selected K days was used for prediction. In this study, the weighted average method is used and the neighboring distance is used as the weight.…”

mentioning

confidence: 99%

Entropy-Weight-Method-Based Integrated Models for Short-Term Intersection Traffic Flow Prediction

Li²,

Song³

et al. 2022

Entropy

Self Cite

View full text Add to dashboard Cite

Three different types of entropy weight methods (EWMs), i.e., EWM-A, EWM-B, and EWM-C, have been used by previous studies for integrating prediction models. These three methods use very different ideas on determining the weights of individual models for integration. To evaluate the performances of these three EWMs, this study applied them to developing integrated short-term traffic flow prediction models for signalized intersections. At first, two individual models, i.e., a k-nearest neighbors (KNN)-algorithm-based model and a neural-network-based model (Elman), were developed as individual models to be integrated using EWMs. These two models were selected because they have been widely used for traffic flow prediction and have been approved to be able to achieve good performance. After that, three integrated models were developed by using the three different types of EWMs. The performances of the three integrated models, as well as the individual KNN and Elman models, were compared. We found that the traffic flow predicted with the EWM-C model is the most accurate prediction for most of the days. Based on the model evaluation results, the advantages of using the EWM-C method were deliberated and the problems with the EWM-A and EWM-B methods were also discussed.

show abstract

Short-Term Intersection Traffic Flow Forecasting

Cited by 22 publications

References 43 publications

Evaluation of Rainfall Erosivity Factor Estimation Using Machine and Deep Learning Models

Evaluation of Rainfall Erosivity Factor Estimation Using Machine and Deep Learning Models

Reclaimed water application to vegetation restoration in mining area: Determination of water quality standards and optimization of moderate treatment technology

Entropy-Weight-Method-Based Integrated Models for Short-Term Intersection Traffic Flow Prediction

Contact Info

Product

Resources

About